CN116257745B - Load current extreme abnormality data processing method and device - Google Patents
Load current extreme abnormality data processing method and device Download PDFInfo
- Publication number
- CN116257745B CN116257745B CN202310521045.2A CN202310521045A CN116257745B CN 116257745 B CN116257745 B CN 116257745B CN 202310521045 A CN202310521045 A CN 202310521045A CN 116257745 B CN116257745 B CN 116257745B
- Authority
- CN
- China
- Prior art keywords
- data
- current
- load current
- extreme
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000005856 abnormality Effects 0.000 title claims abstract description 17
- 238000003672 processing method Methods 0.000 title claims abstract description 8
- 230000002159 abnormal effect Effects 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000009499 grossing Methods 0.000 claims abstract description 25
- 238000012216 screening Methods 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 33
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 11
- 230000003203 everyday effect Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/0092—Arrangements for measuring currents or voltages or for indicating presence or sign thereof measuring current only
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
- G01R19/16528—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values using digital techniques or performing arithmetic operations
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to a load current extreme abnormality data processing method and a device, wherein the load current extreme abnormality data processing method comprises the following steps: acquiring historical data of load current of an authorized user in a preset time period; screening out extreme abnormal current data from the historical data, and performing first-round data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; carrying out data reconstruction on the screening residual data of the current one-dimensional data and the historical data to obtain current two-dimensional data; the current two-dimensional data are imported into a preset Gaussian filter, and a second round of data smoothing is carried out to obtain smooth current data after Gaussian filtering; and further, the extreme abnormal data in the load current can be effectively removed, so that the load current data is smoother, the current operation change and rule can be observed and mastered, and meanwhile, the load state identification and monitoring can be facilitated, and the load current monitoring method has a wide application prospect.
Description
Technical Field
The application relates to the field of power systems, in particular to a method and a device for processing load current extreme abnormality data.
Background
In recent years, with the continuous improvement of national economy and living standard of people, industrial electricity and residential electricity are continuously increased, and industrial electrical equipment and household appliances are increasingly increased; meanwhile, due to the development of the intelligent power grid, the intelligent propulsion of the power distribution side also enables the low-voltage user terminal to realize synchronous optimization, and along with the increase of the power consumption and the nonlinear power consumption load in the power system, the problems about load state identification and monitoring are also widely focused by researchers in recent years.
In the current load state identification and monitoring of a user, because of too much initial noise in load current data of the user, data jitter is severe, a large amount of extreme abnormal data is generated, the observation of data rules is not facilitated, and the extreme abnormal data can also generate larger interference on the load state identification and monitoring.
Aiming at the problem that the influence of extremely abnormal data on data analysis is large because the prior art lacks a method for effectively processing extremely abnormal data, no effective solution is proposed at present.
Disclosure of Invention
The application aims to solve the technical problem that the defect that the influence of extremely abnormal data on data analysis is large due to the lack of an effective method for processing extremely abnormal data in the prior art is overcome, so that the method and the device for processing the extremely abnormal data of load current are provided.
In order to achieve the above purpose, the application adopts the following technical scheme:
on one hand, the application provides a method for processing load current extreme abnormality data, which comprises the following steps: acquiring historical data of load current of an authorized user in a preset time period; screening out extreme abnormal current data from the historical data, and performing first-round data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; carrying out data reconstruction on the screening residual data of the current one-dimensional data and the historical data to obtain current two-dimensional data; and importing the current two-dimensional data into a preset Gaussian filter, and performing second-round data smoothing to obtain smoothed current data after Gaussian filtering.
Optionally, obtaining the historical data of the load current of the authorized user in the preset time period includes: acquiring load current data of a preset time interval of an authorized user, and acquiring load current data of a preset number of time points every day; and taking the load current data of the preset time interval and the load current data of the preset time points as historical data.
Optionally, screening the historical data for the extreme abnormal current data includes: in the three-phase current, if the load current of the first phase is smaller than a preset value or the load current of the first phase is larger than a preset value and the load current of the first phase is a preset multiple of the load current of the second phase or the load currents of the second phase and the third phase at the same moment, the data of the load current of the first phase at the moment is extremely abnormal current data.
Optionally, performing a first round of data smoothing on the pole end abnormal current data to obtain current one-dimensional data arranged in time sequence includes: acquiring front and back N continuous load current data of the extreme abnormal current data in the historical data by taking the extreme abnormal current data as a midpoint, and obtaining a first data set of 2N+1 points; sequencing the first data set according to the current value to obtain a second data set; the median value of the second data set is taken as current one-dimensional data of the extreme abnormal current.
Optionally, the data reconstruction includes:
（1）
wherein d 1 、d 2 、……、d i The unit is day, which is the preset time; t is t 1 、t 2 、……、t 96 The time points are the preset intervals; dn is a current numerical matrix of all time points of i days; thenLoad current data expressed as day 2, time 1.
Optionally, the current two-dimensional data is led into a preset gaussian filter, the second round of data smoothing is performed, and obtaining smoothed current data after gaussian filtering includes: constructing a Gaussian filter template; substituting standard deviation sigma of Gaussian distribution into a Gaussian filter template to obtain a weight matrix; respectively importing the current two-dimensional data into a weight matrix, and calculating to obtain a Gaussian blur value; the total gaussian blur values are collected and smoothed current data is obtained.
Further optionally, constructing the gaussian filter template includes: sampling by taking the central position of the template as the origin of coordinates to construct a Gaussian filter template of (2k+1) x (2k+1), wherein the calculation formula of each element value in the Gaussian filter template comprises:
（2）
in the formula (2), i is the abscissa of the Gaussian filter template; j is the ordinate of the Gaussian filter template;the element value of the H coordinate point in the Gaussian filter template; sigma is the standard deviation of the gaussian distribution; k is a constant, and the value range comprises 1, 2, … … and 47; e. pi is a natural constant.
Further alternatively, the standard deviation σ of the gaussian distribution is obtained by Grid Search exhaustive Search.
On the other hand, the application also provides a load current extreme abnormality data processing device, which comprises: the acquisition module is used for acquiring historical data of the load current of the authorized user in a preset time period; the first data processing module is used for screening out extreme abnormal current data from the historical data, and performing first round of data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; the reconstruction module is used for carrying out data reconstruction on the screening residual data of the current one-dimensional data and the historical data to obtain current two-dimensional data; and the second data processing module is used for guiding the current two-dimensional data into a preset Gaussian filter, and performing second-round data smoothing to obtain smoothed current data after Gaussian filtering.
Optionally, the obtaining module is specifically configured to: acquiring load current data of a preset time interval of an authorized user, and acquiring load current data of a preset number of time points every day; and taking the load current data of the preset time interval and the load current data of the preset time points as historical data.
Compared with the prior art, the application has the beneficial effects that:
the method and the device for processing the load current extreme abnormality data are provided in the technical scheme. Acquiring historical data of load current of an authorized user in a preset time period; screening out extreme abnormal current data from the historical data, and performing first-round data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; carrying out data reconstruction on the screening residual data of the current one-dimensional data and the historical data to obtain current two-dimensional data; the current two-dimensional data are imported into a preset Gaussian filter, and a second round of data smoothing is carried out to obtain smooth current data after Gaussian filtering; and further, the extreme abnormal data in the load current can be effectively removed, so that the load current data is smoother, the current operation change and rule can be observed and mastered, and meanwhile, the load state identification and monitoring can be facilitated, and the load current monitoring method has a wide application prospect.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a method for processing load current extreme anomaly data according to an embodiment of the present application.
FIG. 2 is a graph showing the comparison of current before and after processing of load current extreme anomaly data according to the present application.
Fig. 3 is a schematic diagram of a load current extreme anomaly data processing apparatus according to a second embodiment of the present application.
Detailed Description
The present application will be described and illustrated with reference to the accompanying drawings and examples in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. All other embodiments, which can be made by a person of ordinary skill in the art based on the embodiments provided by the present application without making any inventive effort, are intended to fall within the scope of the present application.
It is apparent that the drawings in the following description are only some examples or embodiments of the present application, and it is possible for those of ordinary skill in the art to apply the present application to other similar situations according to these drawings without inventive effort. Moreover, it should be appreciated that while such a development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as having the benefit of this disclosure.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by those of ordinary skill in the art that the described embodiments of the application can be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," and similar referents in the context of the application are not to be construed as limiting the quantity, but rather as singular or plural. The terms "comprising," "including," "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to only those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in connection with the present application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The terms "first," "second," "third," and the like, as used herein, are merely distinguishing between similar objects and not representing a particular ordering of objects.
Example 1
The embodiment of the application provides a method for processing load current extreme abnormality data, and fig. 1 is a schematic diagram of a method for processing load current extreme abnormality data provided by the first embodiment of the application; in the current load state identification and monitoring of a user, as the initial noise in the load current data of the user is too much, the data jitter is severe, a large amount of extreme abnormal data is generated, the observation of a data rule is not facilitated, and the extreme abnormal data can also generate larger interference on the load state identification and monitoring, the data needs to be smoothed, and the extreme abnormal data in the data is removed; as shown in fig. 1, the method for processing load current extreme anomaly data provided by the embodiment of the application includes:
s102, acquiring historical data of load current of an authorized user in a preset time period; in this embodiment, the obtaining the historical data of the load current of the authorized user within the preset time period specifically includes: acquiring load current data of an authorized user at 15-minute intervals (i.e., preset time intervals in the application), and acquiring load current data of 96 time points (i.e., preset number of time points in the application) every day; load current data at 15 minute intervals and load current data at 96 time points are taken as historical data;
s104, extreme abnormal current data are screened out from the historical data, and first-round data smoothing is carried out on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence;
further, in this embodiment, the screening of the extremely abnormal current data from the history data specifically includes: in the three-phase current, if the load current of the first phase is less than 0A or the load currents of the first phase, the second phase and the third phase are all greater than 0A, and the load current of the first phase is 150 times (i.e. a preset multiple in the application) that of the second phase or the second phase and the third phase, the data of the load current of the first phase at the moment is extremely abnormal current data; similarly, if the load current of the second phase is less than 0A, or the load currents of the first phase, the second phase and the third phase are all greater than 0A, and the load current of the second phase is 150 times that of the first phase or the first phase and the third phase, the data of the load current of the second phase at the moment point is extremely abnormal current data; if the load current of the third phase is less than 0A, or the load currents of the first phase, the second phase and the third phase are all greater than 0A, and the load current of the third phase is 150 times of the load current of the first phase or the load currents of the first phase and the second phase, the data of the load current of the third phase at the moment point is extremely abnormal current data;
further, in this embodiment, performing the first round of data smoothing on the pole end abnormal current data to obtain current one-dimensional data arranged in time sequence specifically includes: acquiring front and back N continuous load current data of the extreme abnormal current data in the historical data by taking the extreme abnormal current data as a midpoint, and obtaining a first data set of 2N+1 points; sequencing the first data set according to the current value to obtain a second data set; the median value of the second data set is taken as current one-dimensional data of the extreme abnormal current.
S106, carrying out data reconstruction on the screening residual data of the current one-dimensional data and the historical data to obtain current two-dimensional data; in this embodiment, the data reconstruction specifically includes:
（1）
wherein d 1 、d 2 、……、d i The unit is day, which is the preset time; t is t 1 、t 2 、……、t 96 The time points are time points, and the interval between the adjacent time points is 15 minutes; dn is a current numerical matrix of all time points of i days; thenLoad current data expressed as day 2, time 1.
S108, importing the current two-dimensional data into a preset Gaussian filter, and performing second-round data smoothing to obtain smoothed current data after Gaussian filtering; in this embodiment, the step of introducing the current two-dimensional data into a preset gaussian filter to perform the second round of data smoothing, and the step of obtaining the smoothed current data after the gaussian filtering includes:
constructing a Gaussian filter template; in this embodiment, constructing the gaussian filter template specifically includes: sampling by taking the central position of the template as the origin of coordinates to construct a Gaussian filter template of (2k+1) x (2k+1), wherein the calculation formula of each element value in the Gaussian filter template comprises: （2）
in the formula (2), i is the abscissa of the Gaussian filter template; j is the ordinate of the Gaussian filter template;the element value of the H coordinate point in the Gaussian filter template; sigma is the standard deviation of the gaussian distribution; k is a constant, and the value range comprises 1, 2, … … and 47; e. pi is a natural constant.
Substituting standard deviation sigma of Gaussian distribution into a Gaussian filter template to obtain a weight matrix; the most important parameter for generating the Gaussian filter template is the standard deviation sigma of Gaussian distribution, the standard deviation represents the discrete degree of data, if sigma is smaller, the center coefficient of the generated template is larger, the surrounding coefficients are smaller, and the smoothing effect is not obvious; on the contrary, if sigma is larger, the difference of the coefficients of the generated templates is not very large, and the smoothing effect is obvious compared with a similar average template; in this embodiment, the standard deviation σ of the gaussian distribution is obtained through Grid Search exhaustive Search, specifically: each possibility is tried in all candidate parameters sigma through cyclic traversal, a Gaussian filtered curve is drawn, and the final parameters sigma are screened out through image analysis;
respectively importing the current two-dimensional data into a weight matrix, and calculating to obtain a Gaussian blur value;
the total gaussian blur values are collected and smoothed current data is obtained.
In the embodiment, a template of a Gaussian filter is constructed, and discretization is carried out on a Gaussian function, and the obtained Gaussian function value is used as a coefficient of the template; preferably, taking the example of constructing a gaussian filter template that yields a 3 x 3:
in the first step, the coordinates of the template at each position are sampled with the center position of the template as the origin of coordinates, as shown below (x-axis horizontal to the right and y-axis vertical to the bottom).
| （-1,1） | （0,1） | （1,1） |
| （-1,0） | （0,0） | （1,0） |
| （-1,-1） | （0,-1） | （1,-1） |
The coordinates of each location are then brought into a gaussian function, resulting in template coefficients.
Second, setting the value of σ to be 1.5, and then setting the weight matrix with the blur radius of 1 as shown in table 1:
TABLE 1
| 0.0453542 | 0.0566406 | 0.0453542 |
| 0.0566406 | 0.0707355 | 0.0566406 |
| 0.0453542 | 0.0566406 | 0.0453542 |
If the weight sum of the 9 points is equal to 0.4787147, the weight sum of the 9 points is equal to 1 if only the weighted average of the 9 points is calculated, so the values of the 9 points are divided by 0.4787147 to obtain the final weight matrix, as shown in table 2:
TABLE 2
| 0.0947416 | 0.118318 | 0.0947416 |
| 0.118318 | 0.147761 | 0.118318 |
| 0.0947416 | 0.118318 | 0.0947416 |
And a third step of: respectively importing the current two-dimensional data into a weight matrix of the table 2, and calculating Gaussian blur values; three identical time points for three consecutive days were taken, and a total of 9 current values were taken, as shown in table 3:
TABLE 3 Table 3
| 0.633 | 0 | 0.641 |
| 0.241 | 1.141 | 0.158 |
| 0.641 | 0.433 | 0.447 |
Each point in table 3 is multiplied by a corresponding weight value in the matrix obtained in table 2:
| 0.633*0.0947416 | 0*0.118318 | 0.641*0.0947416 |
| 0.241*0.118318 | 1.141*0.147761 | 0.158*0.118318 |
| 0.641*0.0947416 | 0.433*0.118318 | 0.447*0.0947416 |
the results are shown in Table 4:
TABLE 4 Table 4
| 0.05997 | 0 | 0.06073 |
| 0.02851 | 0.16860 | 0.01869 |
| 0.06073 | 0.05123 | 0.04235 |
Adding up the 9 values in table 4, the gaussian blur value of the center point is obtained.
Fourth, repeating the process for all points, summarizing Gaussian blur values, and finally obtaining smooth current data after Gaussian filtering; referring to fig. 2, the current comparison diagrams before and after the processing of the load current extreme abnormality data show that the load current data is smoother after the processing of the load current extreme abnormality data, thereby being beneficial to observing and grasping the current operation change and rule and being beneficial to identifying and monitoring the load state.
It should be noted that, the above values in the method for processing load current extreme anomaly data provided by the embodiment of the present application are only described as an optimal example, so that the method for processing load current extreme anomaly data provided by the embodiment of the present application is implemented, and the method is not limited specifically.
By adopting the processing method for the extreme abnormal data of the load current, the extreme abnormal data in the load current can be effectively removed, so that the load current data is smoother, the observation and grasp of the current operation change and rule are facilitated, and meanwhile, the load state identification and monitoring are facilitated, so that the processing method has a wide application prospect.
Example two
An embodiment of the present application provides a load current extreme abnormality data processing device, and fig. 3 is a schematic diagram of a load current extreme abnormality data processing device provided in a second embodiment of the present application; as shown in fig. 3, the load current extreme anomaly data processing apparatus provided by the embodiment of the present application includes: the acquiring module 302 is configured to acquire historical data of a load current of an authorized user within a preset duration; the first data processing module 304 is configured to screen out extreme abnormal current data from the historical data, and perform a first round of data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; the reconstruction module 306 is configured to perform data reconstruction on the screened residual data of the current one-dimensional data and the historical data to obtain current two-dimensional data; and the second data processing module 308 is configured to guide the current two-dimensional data into a preset gaussian filter, and perform a second round of data smoothing to obtain smoothed current data after gaussian filtering.
In this embodiment, the obtaining module 302 is specifically configured to: acquiring load current data of a preset time interval of an authorized user, and acquiring load current data of a preset number of time points every day; and taking the load current data of the preset time interval and the load current data of the preset time points as historical data.
It should be noted that, the load current extreme abnormality data processing device provided by the embodiment of the present application is only described by taking the above example as an example, so as to implement the load current extreme abnormality data processing method provided by the embodiment of the present application, and the method is not limited specifically.
The above embodiments are only preferred embodiments of the present application, and the scope of the present application is not limited thereto, but any insubstantial changes and substitutions made by those skilled in the art on the basis of the present application are intended to be within the scope of the present application as claimed.
Claims (8)
1. A method for processing load current extreme anomaly data, comprising:
acquiring historical data of load current of an authorized user in a preset time period;
screening out extreme abnormal current data from the historical data, and performing first-round data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; the first-round data smoothing is performed on the extremely abnormal current data, and the current one-dimensional data arranged in time sequence is obtained, wherein the method comprises the following steps of:
taking the extreme abnormal current data as a midpoint, acquiring front and back N continuous load current data of the extreme abnormal current data in the historical data, and obtaining a first data set of 2N+1 points;
sequencing the first data set according to the current value to obtain a second data set;
taking the median value of the second data set as the current one-dimensional data of the extreme abnormal current;
carrying out data reconstruction on the current one-dimensional data and the screening residual data of the historical data to obtain current two-dimensional data; wherein the data reconstruction comprises:
（1）
in the formula (1), d 1 、d 2 、……、d i The unit is day, which is the preset time; t is t 1 、t 2 、……、t 96 The time points are the preset intervals; dn is a current numerical matrix of all time points of i days; thenLoad current data expressed as day 2, time 1;
and importing the current two-dimensional data into a preset Gaussian filter, and performing second-round data smoothing to obtain smoothed current data after Gaussian filtering.
2. The method for processing load current extreme anomaly data according to claim 1, wherein the obtaining the historical data of the load current of the authorized user within the preset time period comprises:
acquiring load current data of a preset time interval of the authorized user, and acquiring the load current data of a preset number of time points every day;
and taking the load current data of the preset time interval and the load current data of the preset number of time points as the historical data.
3. The load current extreme anomaly data processing method of claim 1, wherein: the screening of the extreme abnormal current data from the historical data comprises:
in the three-phase current, if the load current of the first phase is smaller than the preset value or the load current of the first phase is larger than the preset value, and the load current of the first phase is a preset multiple of the load current of the second phase or the second phase and the third phase,
the data of the first phase load current at this point in time is the extreme abnormal current data.
4. The method for processing load current extreme anomaly data according to claim 1, wherein the step of introducing the current two-dimensional data into a preset gaussian filter to perform a second round of data smoothing, and obtaining smoothed current data after gaussian filtering comprises:
constructing a Gaussian filter template;
substituting standard deviation sigma of Gaussian distribution into the Gaussian filter template to obtain a weight matrix;
respectively importing the current two-dimensional data into the weight matrix, and calculating to obtain a Gaussian blur value;
and summarizing the Gaussian blur values to obtain smooth current data.
5. The method of claim 4, wherein constructing a gaussian filter template comprises:
sampling by taking the central position of the template as the origin of coordinates, and constructing a Gaussian filter template of (2k+1) x (2k+1), wherein a calculation formula of each element value in the Gaussian filter template comprises:
（2）
in the formula (2), i is the abscissa of the Gaussian filter template; j is the ordinate of the Gaussian filter template;the element value of the H coordinate point in the Gaussian filter template is obtained; sigma is the standard deviation of the gaussian distribution; k is a constant, and the value range comprises 1, 2, … … and 47; e. pi is a natural constant.
6. The method for processing load current extreme anomaly data according to claim 4, wherein the standard deviation σ of the gaussian distribution is obtained by Grid Search exhaustive Search.
7. A load current extreme abnormality data processing apparatus, comprising:
the acquisition module is used for acquiring historical data of the load current of the authorized user in a preset time period;
the first data processing module is used for screening out extreme abnormal current data from the historical data, and performing first round of data smoothing on the extreme abnormal current data to obtain current one-dimensional data arranged in time sequence; the first-round data smoothing is performed on the extremely abnormal current data, and the current one-dimensional data arranged in time sequence is obtained, wherein the method comprises the following steps of:
taking the extreme abnormal current data as a midpoint, acquiring front and back N continuous load current data of the extreme abnormal current data in the historical data, and obtaining a first data set of 2N+1 points;
sequencing the first data set according to the current value to obtain a second data set;
taking the median value of the second data set as the current one-dimensional data of the extreme abnormal current;
the reconstruction module is used for carrying out data reconstruction on the current one-dimensional data and the screening residual data of the historical data to obtain current two-dimensional data; wherein the data reconstruction comprises:
（1）
in the formula (1), d 1 、d 2 、……、d i The unit is day, which is the preset time; t is t 1 、t 2 、……、t 96 The time points are the preset intervals; dn is a current numerical matrix of all time points of i days; thenLoad current data expressed as day 2, time 1;
and the second data processing module is used for guiding the current two-dimensional data into a preset Gaussian filter to carry out second-round data smoothing to obtain smoothed current data after Gaussian filtering.
8. The load current extreme anomaly data processing device of claim 7, wherein the acquisition module is specifically configured to:
acquiring load current data of a preset time interval of the authorized user, and acquiring the load current data of a preset number of time points every day;
and taking the load current data of the preset time interval and the load current data of the preset number of time points as the historical data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310521045.2A CN116257745B (en) | 2023-05-10 | 2023-05-10 | Load current extreme abnormality data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310521045.2A CN116257745B (en) | 2023-05-10 | 2023-05-10 | Load current extreme abnormality data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116257745A CN116257745A (en) | 2023-06-13 |
| CN116257745B true CN116257745B (en) | 2023-08-15 |
Family
ID=86688273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310521045.2A Active CN116257745B (en) | 2023-05-10 | 2023-05-10 | Load current extreme abnormality data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116257745B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930595B (en) * | 2023-09-18 | 2023-11-24 | 法拉迪电气有限公司 | Accurate data metering method for new energy grid-connected voltage regulation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101534933A (en) * | 2006-05-26 | 2009-09-16 | 沃特世科技公司 | Ion detection and parameter estimation for n-dimensional data |
| CN107423769A (en) * | 2017-08-03 | 2017-12-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
| CN110533257A (en) * | 2019-09-05 | 2019-12-03 | 天津华春智慧能源科技发展有限公司 | Prediction method for district heating load |
| CN112326213A (en) * | 2019-08-05 | 2021-02-05 | 株式会社理光 | Abnormal data detection method and device and mechanical fault detection method and device |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
| CN115600837A (en) * | 2022-11-02 | 2023-01-13 | 国网山东省电力公司营销服务中心（计量中心）（Cn） | Energy-saving diagnosis method for load abnormity of electric appliance |
| CN115952878A (en) * | 2022-07-29 | 2023-04-11 | 上海玫克生储能科技有限公司 | Power load prediction method and device, electronic equipment and storage medium |
| CN116011647A (en) * | 2023-01-05 | 2023-04-25 | 华润数字科技有限公司 | Gas load prediction method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020237539A1 (en) * | 2019-05-29 | 2020-12-03 | 西门子股份公司 | Power load prediction method and apparatus, and storage medium |
-
2023
- 2023-05-10 CN CN202310521045.2A patent/CN116257745B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101534933A (en) * | 2006-05-26 | 2009-09-16 | 沃特世科技公司 | Ion detection and parameter estimation for n-dimensional data |
| CN107423769A (en) * | 2017-08-03 | 2017-12-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
| EP3968247A1 (en) * | 2019-06-21 | 2022-03-16 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
| CN112326213A (en) * | 2019-08-05 | 2021-02-05 | 株式会社理光 | Abnormal data detection method and device and mechanical fault detection method and device |
| CN110533257A (en) * | 2019-09-05 | 2019-12-03 | 天津华春智慧能源科技发展有限公司 | Prediction method for district heating load |
| WO2021164267A1 (en) * | 2020-02-21 | 2021-08-26 | 平安科技（深圳）有限公司 | Anomaly detection method and apparatus, and terminal device and storage medium |
| CN115952878A (en) * | 2022-07-29 | 2023-04-11 | 上海玫克生储能科技有限公司 | Power load prediction method and device, electronic equipment and storage medium |
| CN115600837A (en) * | 2022-11-02 | 2023-01-13 | 国网山东省电力公司营销服务中心（计量中心）（Cn） | Energy-saving diagnosis method for load abnormity of electric appliance |
| CN116011647A (en) * | 2023-01-05 | 2023-04-25 | 华润数字科技有限公司 | Gas load prediction method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 异常电力负荷数据的辨识方法研究;任丽娜;芮执元;刘彦新;徐龙云;;水力发电(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116257745A (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116257745B (en) | Load current extreme abnormality data processing method and device | |
| CN115575754B (en) | Intelligent industrial park electricity consumption anomaly identification method and system | |
| CN106980044B (en) | A kind of Harmonious Waves in Power Systems current estimation method adapting to wind power integration | |
| CN106908668B (en) | Processing method and system for actually measured ground synthetic electric field data | |
| CN109828227A (en) | A kind of electronic current mutual inductor method for diagnosing faults based on current information feature | |
| CN111711677A (en) | Virtual and real loop visualization method, system and medium for process layer switch of intelligent substation | |
| CN106910140A (en) | A kind of method based on SVG form power system wiring diagram Network topologies | |
| CN116796403A (en) | Building energy saving method based on comprehensive energy consumption prediction of commercial building | |
| CN117614141B (en) | Multi-voltage-level coordination management method for power distribution network | |
| WO2024104037A1 (en) | Direct-current arc detection method based on mathematical morphology and mode recognition | |
| CN110413622B (en) | Data processing method based on electric power big data platform | |
| CN106849154B (en) | Photovoltaic power station node harmonic voltage and harmonic source sensitivity relation analysis method | |
| CN115600494A (en) | Low-voltage distribution area topology automatic identification method and device | |
| CN112787322B (en) | Dynamic power grid management method based on scada system and multiple time scales | |
| CN114860706A (en) | Power distribution network measurement data cleaning method based on space-time combination | |
| CN111539275B (en) | Electrical load classification method and system based on load characteristic visualization | |
| CN117332359B (en) | Power data transmission abnormality detection method and system | |
| CN109193645B (en) | Data-driven annular power grid reactance parameter evaluation method and evaluation system | |
| CN108564249B (en) | Power distribution network confidence peak clipping benefit evaluation method considering distributed photovoltaic randomness | |
| CN108255142B (en) | Quality of production control method and device | |
| CN110245617A (en) | Artificial intelligence analysis's method based on transient state recording waveform | |
| CN110244183A (en) | A kind of feeder line section health degree calculation method and system | |
| CN115360726B (en) | Method and system for identifying key influencing factors of subsynchronous oscillation propagation | |
| CN114048809B (en) | Series-parallel power distribution network adaptive planning method and device considering interval voltage beyond limit | |
| CN114047372B (en) | Voltage characteristic-based platform region topology identification system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and device for processing extreme abnormal data of load current Granted publication date: 20230815 Pledgee: Wenzhou Bank Co.,Ltd. Hangzhou Branch Pledgor: HANGZHOU ZHICHENG ELECTRONIC TECHNOLOGY Co.,Ltd. Registration number: Y2024330000166 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |